SHI Jian's Projects
TensorFlow 2.x version's Tutorials and Examples, including CNN, RNN, GAN, Auto-Encoders, FasterRCNN, GPT, BERT examples, etc. TF 2.0版入门实例代码,实战教程。
Train a object detection model with the Tensorflow Object Detection API and Tensorflow 2.
tensorflow2中文教程,持续更新(当前版本:tensorflow2.0),tag: tensorflow 2.0 tutorials
A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection
A WebGL accelerated, browser based JavaScript library for training and deploying ML models.
A dataset of traffic, fire and accident images for training deep learning models.
Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision
A Large-Scale Dataset for Vehicle Re-Identification in the Wild
To classify video into various classes using keras library with tensorflow as back-end.
a plugin-oriented framework for video structured. 国产程序员请加微信zhzhi78拉群交流。
Classify images offline using Watson Visual Recognition and Core ML
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments
A simple, fully convolutional model for real-time instance segmentation.
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
yolo 4th edition implemented by tensorflow2.0
You Only Look Once for Panopitic Driving Perception.(https://arxiv.org/abs/2108.11250)
You Only Look at One Sequence (https://arxiv.org/abs/2106.00666)
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏
在 oxford hand 数据集上对 YOLOv3 做模型剪枝(network slimming)
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.
这是一个YoloV4-pytorch的源码,可以用于训练自己的模型。
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Yet another yolov5, with its runtime stack for libtorch, onnx and specialized accelerators. You like torchvision's retinanet? You like yolov5? You love yolov5rt!
Real-time multi-person tracker using YOLO v5 and deep sort
YOLOv6: a single-stage object detection framework dedicated to industrial application.
🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥